Stress Modelling Using Transfer Learning in Presence of Scarce Data

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9456)


Stress at work is a significant occupational health concern nowadays. Thus, researchers are looking to find comprehensive approaches for improving wellness interventions relevant to stress. Recent studies have been conducted for inferring stress in labour settings; they model stress behaviour based on non-obtrusive data obtained from smartphones. However, if the data for a subject is scarce, a good model cannot be obtained. We propose an approach based on transfer learning for building a model of a subject with scarce data. It is based on the comparison of decision trees to select the closest subject for knowledge transfer. We present an study carried out on 30 employees within two organisations. The results show that the in the case of identifying a “similar” subject, the classification accuracy is improved via transfer learning.


Stress modelling Transfer learning Semi-supervised learning 



The work on this paper was partially funded by EC Marie Curie IRSES Project UBIHEALTH - 316337.


  1. 1.
    Agence européenne pour la sécurité et la santé au travail, Malgorzata Milczarek, Eusebio Rial-González, and Elke Schneider. Occupational safety and health in figures: stress at work-facts and figures. Office for Official Publications of the European Communities (2009)Google Scholar
  2. 2.
    Näätänen, P., Kiuru, V.: Bergen burnout indicator 15. Edita (2003)Google Scholar
  3. 3.
    Ceja, E., Osmani, V., Mayora, O.: Automatic stress detection in working environments from smartphones’ accelerometer data: a first step. IEEE J. Biomed. Health Inform. PP(99), 1 (2015)Google Scholar
  4. 4.
    Osmani, V.: Smartphones in mental health: detecting depressive and manic episodes. IEEE Pervasive Comput. 14(3), 10–13 (2015)CrossRefGoogle Scholar
  5. 5.
    Ferdous, R., Osmani, V., Mayora, O.: Smartphone app usage as a predictor of perceived stress levels at workplace. IEEE 8, 20–23 (2015)Google Scholar
  6. 6.
    Grunerbl, A., Muaremi, A., Osmani, V., Bahle, G., Ohler, S., Troster, G., Mayora, O., Haring, C., Lukowicz, P.: Smartphone-based recognition of states and state changes in bipolar disorder patients. IEEE J. Biomed. Health Inf. 19(1), 140–148 (2015)CrossRefGoogle Scholar
  7. 7.
    Bakker, J., Pechenizkiy, M., Sidorova, N.: What’s your current stress level? detection of stress patterns from gsr sensor data. In: 2011 IEEE 11th International Conference on Data Mining Workshops, pp. 573–580. IEEE (2011)Google Scholar
  8. 8.
    Liu, K.K-L.: A personal, mobile system for understanding stress and interruptions. Master’s thesis, MIT Media Arts and Science (2004)Google Scholar
  9. 9.
    Lu, H., Frauendorfer, D., Rabbi, M., Mast, M.S., Chittaranjan, G.T., Campbell, A.T., Gatica-Perez, D., Choudhury, T.: Stresssense: detecting stress in unconstrained acoustic environments using smartphones. In: Proceedings of the 2012 ACM Conference on Ubiquitous Computing, pp. 351–360 (2012)Google Scholar
  10. 10.
    Kocielnik, R., Sidorova, N., Maggi, F.M., Ouwerkerk, M., Westerink, J.H.D.M.: Smart technologies for long-term stress monitoring at work. In: 2013 IEEE 26th International Symposium on Computer-Based Medical Systems, pp. 53–58 (2013)Google Scholar
  11. 11.
    Likamwa, R., Liu, Y., Lane, N.D., Zhong, L.: Moodscope: building a mood sensor from smartphone usage patterns. In Proceeding of the 11th Annual International Conference on Mobile Systems, Applications, and Services, pp. 389–402 (2013)Google Scholar
  12. 12.
    Bauer, G., Lukowicz, P.: Can smartphones detect stress-related changes in the behaviour of individuals? In: 2012 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops), pp. 423–426 (2012)Google Scholar
  13. 13.
    Bogomolov, A., Lepri, B., Ferron, M., Pianesi, F., Pentland, A.S.: Daily stress recognition from mobile phone data, weather conditions and individual traits. In: Proceedings of the ACM International Conference on Multimedia, pp. 477–486 (2014)Google Scholar
  14. 14.
    Zhu, X.: Semi-supervised learning. In: Sammut, C., Webb, G.I. (eds.) Encyclopedia of Machine Learning, pp. 892–897. Springer, Heidelberg (2010)Google Scholar
  15. 15.
    Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)CrossRefGoogle Scholar
  16. 16.
    Demerouti, E., Bakker, A.B.: The oldenburg burnout inventory: a good alternative to measure burnout and engagement. Handbook of stress and burnout in health care. Hauppauge, NY: Nova Science (2008)Google Scholar
  17. 17.
    FUNF - Open Sensing Framework (2014).
  18. 18.
    Birant, D., Kut, A.: St-dbscan: an algorithm for clustering spatial-temporal data. Data Knowl. Eng. 60(1), 208–221 (2007)CrossRefGoogle Scholar
  19. 19.
    Robusto, C.C.: The cosine-haversine formula. Am. Math. Mon. 64(1), 38–40 (1957)MathSciNetCrossRefGoogle Scholar
  20. 20.
    Hedelin, P., Huber, D.: Pitch period determination of aperiodic speech signals. In: 1990 International Conference on Acoustics, Speech, and Signal Processing, 1990, ICASSP-90, pp. 361–364. IEEE (1990)Google Scholar
  21. 21.
    Harris, F.J.: On the use of windows for harmonic analysis with the discrete fourier transform. Proc. IEEE 66(1), 51–83 (1978)CrossRefGoogle Scholar
  22. 22.
    Quinlan, J.R.: C4.5 Programs for Machine Learning. Morgan Kaufmann, San Mateo (1993)Google Scholar
  23. 23.
    Miglio, R., Soffritti, G.: The comparison between classification trees through proximity measures. Comput. Stat. Data Anal. 45(3), 577–593 (2004)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  1. 1.Instituto Nacional de Astrofísica, Óptica y ElectrónicaSta. María TonantzintlaMexico
  2. 2.CREATE-NETTrentoItaly

Personalised recommendations